Abstract
Research on unsupervised word sense discrimination typically ignores a notable dynamic aspect, whereby the prevalence of a word sense varies over time, to the point that a given word (such as ’tweet’) can acquire a new usage alongside a pre-existing one (such as ’a Twitter post’ alongside ’a bird noise’). This work applies unsupervised methods to text collections within which such neologisms can reasonably be expected to occur. We propose a probabilistic model which conditions words on senses, and senses on times and an EM method to learn the parameters of the model using data from which sense labels have been deleted. This is contrasted with a static model with no time dependency. We show qualitatively that the learned and the observed time-dependent sense distributions resemble each other closely, and quantitatively that the learned dynamic model achieves a higher tagging accuracy (82.4%) than the learned static model does (76.1%).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Blei, D.M., Lafferty, J.D.: Dynamic topic models. In: Cohen, W., Moore, A. (eds.) ICML 2006: Proceedings of the 23rd International Conference on Machine Learning, pp. 113–120. ACM Press, New York (2006)
Maldonado-Guerra, A., Emms, M.: First-order and second-order context representations: geometrical considerations and performance in word-sense disambiguation and discrimination. In: Dister, A., Dominique Longrée, G.P. (eds.) Proceeding of JADT 11th International Conference on the Statistical Analysis of Textual Data, pp. 676–686. LASLA (2012)
Manning, C., Schütze, H.: Word Sense Disambiguation. In: Foundations of Statistical Language Processing, 6th edn., pp. 229–264. MIT Press (2003)
Manning, C.D., Raghavan, P., Schütze, H.: Language models for information retrieval. In: Introduction to Information Retrieval. Cambridge University Press (2009)
de Marneffe, M.C., Dupont, P.: Comparative study of statistical word sense discrimination. In: Purnelle, G., Fairon, C., Dister, A. (eds.) Proceedings of JADT 2004 7th International Conference on the Statistical Analysis of Textual Data, pp. 270–281. UCL Presses Universitaire de Louvain (2004)
Prescher, D.: A tutorial on the expectation-maximization algorithm including maximum-likelihood estimation and em training of probabilistic context-free grammars. Computing Research Repository (2004)
Purandare, A., Pedersen, T.: Word sense discrimination by clustering contexts in vector and similarity spaces. In: Ng, H.T., Riloff, E. (eds.) Proceedings of CoNLL 2004, Boston, MA, USA, pp. 41–48 (2004)
Sagi, E., Kaufmann, S., Clark, B.: Tracing semantic change with latent semantic analysis. In: Allan, K., Robinson, J.A. (eds.) Current Methods in Historical Semantics, pp. 161–183. Mouton de Gruyter, Berlin (2012)
Schütze, H.: Automatic word sense discrimination. Computational Linguistics 24(1), 97–123 (1998)
Véronis, J.: Hyperlex: lexical cartography for information retrieval. Computer Speech and Language 18(3), 223–252 (2004)
Vickrey, D., Biewald, L., Teyssier, M., Koller, D.: Word-sense disambiguation for machine translation. In: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT 2005, pp. 771–778. Association for Computational Linguistics, Stroudsburg (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Emms, M. (2013). Dynamic EM in Neologism Evolution. In: Yin, H., et al. Intelligent Data Engineering and Automated Learning – IDEAL 2013. IDEAL 2013. Lecture Notes in Computer Science, vol 8206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41278-3_35
Download citation
DOI: https://doi.org/10.1007/978-3-642-41278-3_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41277-6
Online ISBN: 978-3-642-41278-3
eBook Packages: Computer ScienceComputer Science (R0)